Return to search

Inverse Reinforcement Learning and Routing Metric Discovery

Uncovering the metrics and procedures employed by an autonomous networking system is an important problem with applications in instrumentation, traffic engineering, and game-theoretic studies of multi-agent environments. This thesis presents a method for utilizing inverse reinforcement learning (IRL)techniques for the purpose of discovering a composite metric used by a dynamic routing algorithm on an Internet Protocol (IP) network. The network and routing algorithm are modeled as a reinforcement learning (RL) agent and a Markov decision process (MDP). The problem of routing metric discovery is then posed as a problem of recovering the reward function, given observed optimal behavior. We show that this approach is empirically suited for determining the relative contributions of factors that constitute a composite metric. Experimental results for many classes of randomly generated networks are presented. / Master of Science

Identiferoai:union.ndltd.org:VTETD/oai:vtechworks.lib.vt.edu:10919/34728
Date01 September 2003
CreatorsShiraev, Dmitry Eric
ContributorsComputer Science, Ribbens, Calvin J., Varadarajan, Srinidhi, Ramakrishnan, Naren
PublisherVirginia Tech
Source SetsVirginia Tech Theses and Dissertation
Detected LanguageEnglish
TypeThesis
Formatapplication/pdf
RightsIn Copyright, http://rightsstatements.org/vocab/InC/1.0/
Relationetd.pdf

Page generated in 0.0024 seconds